CN106156117B - Hidden community's core communication circle detection towards particular topic finds method and system - Google Patents
Hidden community's core communication circle detection towards particular topic finds method and system Download PDFInfo
- Publication number
- CN106156117B CN106156117B CN201510160958.1A CN201510160958A CN106156117B CN 106156117 B CN106156117 B CN 106156117B CN 201510160958 A CN201510160958 A CN 201510160958A CN 106156117 B CN106156117 B CN 106156117B
- Authority
- CN
- China
- Prior art keywords
- user
- message
- core
- particular topic
- community
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The present invention proposes a kind of hidden community's core communication circle detection towards particular topic and finds method and system.System includes:Key core user's extraction module, including:Message affinities analysis module, user's aggregation module, core customer extract reconstructed module;Key core user, which communicates, encloses extraction module, including:User group relationship module and key user's relationship module.Method comprises the following steps:Establish particular topic message content storehouse;Message in particular topic content-message storehouse is grouped;Obtain the message groups based on similar message;Establish the message in message groups and the mapping of user;Merging is grouped to user, sets corresponding weights, carries key core user;It will extract the virtual linkage network of personal connections being linked to each other two-by-two using key core user as node and enclosed for key core user core communication.Compared with traditional topological organization structure analysis method, quickly it can find and extract and the relevant key core user of theme.
Description
Technical field
Community discovery and tracking field the present invention relates to social networks, are hidden community's core based on particular topic
The method and system that heart communication circle is quickly found.
Background technology
In recent years, as Below-the-line is transferred to line by the extensive extensive use of social networks, people more and more
In upper social networks.Social networks is the physical network being made of many relational links, is played in daily life
Important effect, interacting between user and network accelerate social action to network behavior, society relation to network
The conversion of social relationships and social information to the network information.At present, some microblogging websites (such as Twitter, Sina weibo,
Facebook, Renren Network etc.) gradually rise, the characteristic of social networks is on the one hand represented, user can pay close attention to some users, with
Shi Fabiao, forwarding, comment message etc.;On the other hand media characteristic is demonstrated by, many well-known users issue related new at the first time
After hearing message, these message can be by rapid forwarding and propagation, and the swiftness of this diffusion of information, scale, influence power are
Traditional media is incomparable.More and more society common people express idea or propagate viewpoint, society by social networks
Network is handed over to have the characteristics that exchange is convenient and it is rapid to propagate, information is passed by the large-scale influence power that diffuseed to form of cascade
Broadcast.
In extensive social networks, the key user under precise positioning tracking particular topic, tracking finds particular topic
The recessive community (hidden community) that lower key user is formed, effectively extracts, defines the scale of these hidden communities, affiliated use
Relational network, community's evolving trend at family, to further investigation network particular topic and network interpersonal relationships, network particular topic with
Inherent between them of real interpersonal relationships, online lower interpersonal relationships influences and rule, has important theory and realistic meaning.
Relation of the people formed in social networks, has dominant and recessive point, dominance relation refers to network interaction row
For the linking relationship formed, recessive relation refers to the same or similar spy is discussed between the people without dominant linking relationship
Determine topic, the group spontaneously formed.These surround the relation that specific topics are formed, and become social network relationships in recent years and grind
The hot issue studied carefully, the research of especially recessive relation, even more becomes the emphasis studied.
Based on the research of dominant linking relationship, it is concentrated mainly on Web Community's division, finds relevant algorithm etc., it is early
The community structure partitioning algorithm of phase mainly has figure split plot design (Graph Partition) and hierarchical clustering method (Hierarchical
Clustering, based on sociology) two major classes, wherein figure split plot design are with Kernighan-Lin algorithms and the Laplace based on figure
The spectral bisection method (Spectral Bisection Method) of matrix exgenvalue is representative, and hierarchical clustering is used based on each
The similitude or bonding strength connected between node, social networks is divided, and forms several corporations.In addition, according to
Thinking of addition while removing in network into network, the method for community's division can be divided into splitting method again
(divisive method) and two big classification of condensing method (agglomerative method).Drawn in above-mentioned various networks
In point, either GN algorithms (splitting algorithm), quick community detecting algorithm (NF algorithms), CNM algorithms, or Informap algorithms
All it is in the topology knot based on figure to describe the state of whole the whole network by the multidate information flow graph between node and sideline
On the basis of structure, by spending centrality, close to centrality, betweenness center, eigenvector centrality etc. come calculate node user's
Significance level, divides the linking relationship between user.But the user under topological link structure division particular topic, can not be effective
The similar user group of discovery interest and its recessive community that is formed.
Based on different research angles, also there is researcher from Information Propagation Model, the analog information in social networks
Propagate, carry out the assessment of node influence power by the way of Monte Carlo simulation according to the scope of propagation;Based on diffusion of information
Angle, with bean vermicelli scale number, forwarding scale number, refer to scale number and evaluate the influence power of unique user, Domingos et al.
It is proposed that network influence personal in social networks maximizes, the maximum magnitude reached can be traveled to from the information of the node.
Thoughts of the Weng et al. based on PageRank proposes TwitterRank algorithms, employs the Topic and hair of comprehensive Twitter
The mode of cloth frequency improves probability transfer matrix and (that is to say that the tweets that user delivers under certain Topic is more, transition probability
It is bigger).Just key words are defined as follows in the present invention below:
Towards the hidden community of particular topic:Refer in social networks, those do not have the user of dominant linking relationship
Serial topic under theme is discussed, the recessive group spontaneously formed, they are each other without direct linking relationship or possible
It is not aware that the presence of other side.
Key core user:Refer in the case where discussing theme serial topic, promote during recessive community spontaneously forms, words
Positive promoter, pusher or organizer are inscribed, just the key core user under particular topic in hidden community for this.
Theme:Theme is made of a series of topics, and a theme can include one or more topics.Topic is by keyword
To be indicated.
Core communication circle:Refer to the virtual linkage network of personal connections being made of the key core user in these hidden communities
Network, the hidden community's core communication circle being known as under particular topic, is the frame during whole hidden community structure is formed.
In conclusion the research work of social networks at present is concentrated mainly on three aspects:(opened up with dominant linking relationship
Flutter structural relation) based on community's Research on partition;With user issue message and frequency, user have attribute (profile,
Bean vermicelli number, forwarding number etc.) analyze the scope that user is influenced;The topic discussed with the message content analysis user of user's issue
And its topic model modeling.Although the studies above relate to the community discovery based on linking relationship, user force and scope, words
The technologies such as model modeling are inscribed, but on hidden community definition and discovery, key core user definition and extraction, hidden community's core
Communication circle is found and the technological synthesis application of three aspects of extraction, and especially hidden community's core communication circle is found and extraction skill
Art, is current research blank.
In addition, decision method similar to message content at present has the textual scan strategy based on String matching technology (mainly
For English), although this method processing speed is fast, its there are precision it is not high the shortcomings that, be not particularly suited at Chinese information
Reason, to the method handled using statistics and rule of Chinese information, counts the word frequency after generally use participle or participle, position etc.
Information Statistics, it is regular using semantic, syntax rule, all it is that only content of text is handled no matter using any method,
The generally processing of long text, but literary content (usually only 140 word) is especially pushed away to short message, stop being segmented, being removed
After word, significant descriptor is relatively fewer, and than sparse, the above method is not appropriate for.
The content of the invention
In order to realize hidden community discovery and the extraction under particular topic, the present invention proposes a kind of towards particular topic
Hidden community's core communication circle detection finds method and system.
The system of the present invention includes:
Key core user's extraction module, including:
Message affinities analysis module, to carry out Similarity measures to the message in a particular topic message content storehouse,
And message is grouped according to similitude, obtain the message groups based on similar message;
User's aggregation module, polymerize to establish the message in message groups with the mapping of user;
Core customer extracts reconstructed module, to be grouped according to number of the user across message groups to user, then
Pair merged at the same time across the users of same message groups, and the number (liveness) merged according to user in message groups is to user
Corresponding weights are set, then again from the user after merging using the number across certain message groups as foundation, extract specific master
Key core user under topic;
Key core user, which communicates, encloses extraction module, including:User group relationship module, disappears to extract key core user
Virtual relation between breath group user;Key user's relationship module, to extract key core user and key core user it
Between, the virtual relation between key core user and message groups user;
Hidden community discovery module, comprising customer relationship module, to extract the user after similar message merges and its pass
System;Community discovery module, to extract the hidden relation that key core user message group user is formed.
The method of the present invention includes following steps:
1) particular topic message content storehouse is established;For each specific theme, one group of lists of keywords is set, according to
Lists of keywords is matched with original message content, to establish particular topic message content storehouse.
2) Similarity measures are carried out to the message in particular topic content-message storehouse, and message is divided according to similitude
Group;Obtain the message groups based on similar message;
3) message in message groups and the mapping of user are established;
4) user is grouped across the numbers of message groups according to user, then pair at the same time across the use of same message groups
Family merges, and corresponding weights are set to user, and the user of extraction across a certain number of message groups is under particular topic
Key core user.
5) it will extract the virtual linkage network of personal connections being linked to each other two-by-two using key core user as node and used for key core
The core communication circle at family.
Compared with traditional topological organization structure analysis method, due to by judging to divide by the message affinities of specific user
Class simultaneously carries out mapping polymerization, thus its pair quickly can be found and extract with the relevant key core user of theme.
Brief description of the drawings
Fig. 1 is the system deployment figure of the present invention
Fig. 2 is the main body frame figure of the present invention.
Fig. 3 is the key core user communication circle of the present invention and hidden community discovery process chart.
Fig. 4 is the process chart of key core user of the present invention extraction.
Fig. 5 is hidden community's core key user under certain particular topic in the embodiment of the present invention and topological community experimental result
A mapping graph.
Fig. 6 is hidden community's core key user under certain particular topic in the embodiment of the present invention and topological community experimental result
Another mapping graph
Embodiment
To enable the features described above of the present invention and advantage to become apparent, special embodiment below, and coordinate institute's attached drawing to make
Describe in detail as follows.
The deployment of the system is as shown in Figure 1, the core technology design first to the present invention illustrates, as shown in Fig. 2, originally
The main body frame of invention mainly includes three sub- frame modules, and social networks key core user finds and extraction, particular topic
Under hidden community discovery, key person's core communication circle is found in the hidden community under particular topic.
The present invention towards the key core user of particular topic, hidden community's core communicate circle find, hidden community discovery
Process flow, as shown in figure 3, comprising the following steps:
(1) particular topic message content storehouse is established.One group of lists of keywords is established under particular topic first, with key
Word list is keywords, and message content is matched in origination message storehouse, extraction with the associated message content of keyword,
Message user, news release time, the attribute such as profile of user.
(2) particular topic message library content is subjected to Similarity measures, is grouped with the similitude of message, obtains base
In message user's group of similar message, and establish message groups user mapping.I.e. to the message user of packet, carry out in the same set
Repetition message is rejected, with same user's merging is organized, and the many-one for establishing message and user maps.
(3) by the user group after mapping, the number (at least two) of message user's group is crossed over user, user group is carried out
Merge respectively.Then the duplicate customer in same message groups is merged, and corresponding weights is set to user, it is at this time, right
Across a certain number of message groups user as the key core user under particular topic.
(4) using key core user as node, original similar message user group where key core user is closed
And the message user that outside the message groups of key core user place and message groups user is less than 2 is eliminated, formed with key
Core customer's group is frame, covers the hidden community of the particular topic of all key core users.
(5) using key core user as node, virtual relation network, key core between key core user are built
The virtual relation network of user and message groups user where it, at this time, the void interconnected two-by-two using key core user as node
It is just the core communication circle of key core user to intend linking relationship net.
(6) the key core user based on particular topic is in the mapping relations of hidden community and topological community, extraction key
Community structure where topological relation where core customer.
Above-mentioned steps (two), (three), (four), (five) key core user and core communication circle are the discovery that the core of the present invention
The heart.
Key user core customer extraction process is mainly judged from the similitude of message content, based on similar message group
Map classification syndication users, and finally found that extraction key core user.As shown in Figure 4.
Specifically, the extraction step of key person's core communication circle is as follows in the hidden community under particular topic:
1) all user message similitudes to social networks are judged, are grouped with the similitude of message, obtain base
In message user's group of similar message
2) to across message groups users, it is identified based on the number across message groups
3) across the message groups users under particular topic are identified
4) key core user is extracted, using key core user as node, the virtual linkage relation that interconnects two-by-two is side, structure
Build out the virtual linkage relation between key core user
5) the core communication circle of key core user is extracted
The step of hidden community discovery under particular topic and extraction, is as follows:
1) using key core user as node, extraction and message groups user where key core user and relation.
2) judgement merging is carried out to the duplicate customer in same user group, message based similitude
3) to the message groups user where all key core users, merge, form the hidden society under particular topic
Area.
System explanation
Hidden community system towards particular topic is made of three sub- frame modules, is divided into key core user and is extracted mould
Block, key core user, which communicate, encloses extraction module, hidden community discovery module.
Key core user's extraction module, includes message affinities analysis module, user's aggregation module, core customer's extraction
Reconstructed module etc..Wherein, message affinities analysis module, it is similar to be carried out to the message in a particular topic message content storehouse
Property calculate, and message is grouped according to similitude, obtains the message groups based on similar message;User's aggregation module, to
Establish the message in message groups and the mapping of user;Core customer extracts reconstructed module, to cross over message groups according to user
Then pair number is grouped user, is merged at the same time across the user of same message groups, and user is set corresponding
Weights, to be used across the key core under the user as particular topic of a certain number of message groups.
Key core communication circle extraction module, comprising user group relationship module, to extract key core user message group
Virtual relation between user;Key user's relationship module etc., to extract between key core user and key core user,
Virtual relation between key core user and message groups user.
Hidden community discovery module, comprising customer relationship module, to extract the user after similar message merges and its pass
System;Community discovery module is extracting the hidden relation that key core user message group user is formed.
Good effect
Theory analysis
In social networks, the myspace that is formed based on particular topic, usually based on linking relationship, choosing
The user that associated topic is discussed under theme is taken, is expanded with their linking relationship, is extracted with this and finds community, in this process
In, which user is the organizer, participant, pusher of topic, only can not be analyzed and be defined by linking relationship, in addition,
By linking relationship expand user, be also not necessarily user interested in discussion topic, the community extracted, often with master
The true community of topic has larger deviation, meanwhile, the user based on linking relationship, divide, extracted in community also differs
Surely it is the relevant user of topic, how effectively finds the relevant key core user of topic, the communication circle of key core user,
And the hidden community using them as core, have very important significance, following experiments are also comprehensively demonstrated in this analysis
Theoretical judgment.
Experiment effect
Embodiment:
Data set is the 1G raw message datas of acquisition system collection, totally 2664802 network social intercourse message data, topic
It is divided into 4 topics, each topic is pressed carries out preliminary screening with the degree of correlation of message, is respectively used to the initial data of topic.Often
One topic data represents a topic set.On this basis, by frame model, the hidden community's key core of topic is carried out
User and the discovery and extraction of core communication circle, obtain final experimental result.
From figure 5 it can be seen that hidden community users using topic as core, form multiple communities under particular topic, society
Area forms its institutional framework using key core user as core, and key core user carries out the tissue of topic in hidden community
Or initiate, it is minimum it be also topic the pusher that plays an active part in, such as * xin**, * cao**, L**.In addition can also be from mapping
The division of topological community from the point of view of, * cao**, L** are also big V user, belong to hidden community and topological intercommunal overlapping use
Family, but from the point of view of being subordinated in the overlapping user overall quantity of hidden community and topological community between them, most of key core
User, itself is not big V user (user more than bean vermicelli), big V user is in topic and differs in topological community structure
Surely play the part of critical tissue or initiate role.
Key core user such as * BBC**, * RF**, de** in Fig. 6 as can be seen that hidden community etc., in topological society
It is not Centroid in area, nor big V user, the hidden community that they are formed, in being divided in topological community, in side
Edge role, also side demonstrate key user's circle in hidden community, be not the topological circle that big V user is formed.
It should be noted that associated user's name is only to illustrate in Fig. 5 and Fig. 6, to avoid invading privacy of user, spy does anonymous place
Reason, has no effect on the explanation to technical solution.
Claims (7)
1. a kind of hidden community's core communication circle detection discovery system towards particular topic, including:
Message affinities analysis module, to carry out Similarity measures, and root to the message in a particular topic message content storehouse
Message is grouped according to similitude, obtains the message groups based on similar message;
User's aggregation module, polymerize to establish the message in message groups with the mapping of user;
Core customer extracts reconstructed module, to be grouped according to number of the user across message groups to user, then to same
When merged across the users of same message groups;And corresponding power sets user according to the number that user in message groups merges
Value;Then again from the user after merging using the number across certain message groups as foundation, the crucial core under particular topic is extracted
Heart user;
Key core user, which communicates, encloses extraction module, including:User group relationship module, to extract key core user and message
Virtual relation between group user;Key user's relationship module, to extract between key core user and key core user,
Virtual relation between key core user and message groups user, using key core user as node, the virtual chain that interconnects two-by-two
Side is connected in, constructs the virtual relation between key core user;
One hidden community discovery module, including:Customer relationship module, to extract the user after similar message merges and its pass
System;Community discovery module, to extract the hidden relation that key core user message group user is formed.
2. hidden community's core communication circle detection discovery system according to claim 1 towards particular topic, its feature
It is, by setting one group of lists of keywords for specific theme, is carried out according to lists of keywords and original message content
Match to establish the particular topic message content storehouse.
3. hidden community's core communication circle detection discovery system according to claim 1 towards particular topic, its feature
Be, the message established in message groups polymerize with the mapping of user including:To the message user of packet, in the same set into
Row repetition message is rejected, with same user's merging is organized, and the many-one for establishing message and user maps.
4. hidden community's core communication circle detection discovery system according to claim 1 towards particular topic, its feature
It is, further includes a hidden community discovery module, including:Customer relationship module, to extract the user after similar message merges
And its relation;Community discovery module, to extract the hidden relation that key core user message group user is formed.
5. a kind of hidden community's core communication circle detection discovery method towards particular topic, comprises the following steps:
1) particular topic message content storehouse is established;
2) Similarity measures are carried out to the message in particular topic content-message storehouse, and message is grouped according to similitude;
Obtain the message groups based on similar message;
3) message in message groups and the mapping of user are established, to the message user of packet, carries out repetition message in the same set
Reject, with same user's merging is organized, the many-one for establishing message and user maps;
4) user is grouped across the numbers of message groups according to user, then pair at the same time across same message groups user into
Row merges;And corresponding weights are set to user according to the number that user in message groups merges;Again from the user after merging with
Number across certain message groups is foundation, extracts the key core user under particular topic;
5) will be using key core user as node, virtual relation is linked to each other as side two-by-two, constructs between key core user
Virtual linkage network of personal connections, as key core user core communicate circle.
6. exist as claimed in claim 5 towards hidden community's core communication circle detection discovery method of particular topic, its feature
In the particular topic message content storehouse of establishing includes:For each specific theme, one group of lists of keywords is set, according to
Lists of keywords is matched with original message content, to establish particular topic message content storehouse.
7. exist as claimed in claim 5 towards hidden community's core communication circle detection discovery method of particular topic, its feature
In further including step 6):Topological relation place community structure where extracting key core user is hidden under particular topic
Community.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510160958.1A CN106156117B (en) | 2015-04-07 | 2015-04-07 | Hidden community's core communication circle detection towards particular topic finds method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510160958.1A CN106156117B (en) | 2015-04-07 | 2015-04-07 | Hidden community's core communication circle detection towards particular topic finds method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106156117A CN106156117A (en) | 2016-11-23 |
CN106156117B true CN106156117B (en) | 2018-05-01 |
Family
ID=57338109
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510160958.1A Active CN106156117B (en) | 2015-04-07 | 2015-04-07 | Hidden community's core communication circle detection towards particular topic finds method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106156117B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107038212A (en) * | 2017-02-27 | 2017-08-11 | 中山大学 | A kind of algorithm based on the Converse solved PageRank of monte carlo method |
CN107766515B (en) * | 2017-10-23 | 2020-04-14 | 中国联合网络通信集团有限公司 | Social circle key user extraction method and device |
CN108182639B (en) * | 2017-12-29 | 2021-04-09 | 中国人民解放军火箭军工程大学 | Method and system for determining small group of internet forum |
CN109635134B (en) * | 2018-12-30 | 2023-06-13 | 南京邮电大学盐城大数据研究院有限公司 | Efficient processing flow method for large-scale dynamic graph data |
CN111080463B (en) * | 2019-12-13 | 2022-09-02 | 厦门市美亚柏科信息股份有限公司 | Key communication node identification method, device and medium |
CN112329473B (en) * | 2020-10-20 | 2021-07-30 | 哈尔滨理工大学 | Semantic social network community discovery method based on topic influence seepage |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102347917A (en) * | 2011-11-04 | 2012-02-08 | 西安电子科技大学 | Contact semantic grouping method for network message communication |
CN103020116A (en) * | 2012-11-13 | 2013-04-03 | 中国科学院自动化研究所 | Method for automatically screening influential users on social media networks |
CN103718206A (en) * | 2011-01-04 | 2014-04-09 | 英特尔公司 | Method, system, and computer-readable recording medium for recommending other users or objects by considering preference of at least one user |
CN104239399A (en) * | 2014-07-14 | 2014-12-24 | 上海交通大学 | Method for recommending potential friends in social network |
-
2015
- 2015-04-07 CN CN201510160958.1A patent/CN106156117B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103718206A (en) * | 2011-01-04 | 2014-04-09 | 英特尔公司 | Method, system, and computer-readable recording medium for recommending other users or objects by considering preference of at least one user |
CN102347917A (en) * | 2011-11-04 | 2012-02-08 | 西安电子科技大学 | Contact semantic grouping method for network message communication |
CN103020116A (en) * | 2012-11-13 | 2013-04-03 | 中国科学院自动化研究所 | Method for automatically screening influential users on social media networks |
CN104239399A (en) * | 2014-07-14 | 2014-12-24 | 上海交通大学 | Method for recommending potential friends in social network |
Also Published As
Publication number | Publication date |
---|---|
CN106156117A (en) | 2016-11-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106156117B (en) | Hidden community's core communication circle detection towards particular topic finds method and system | |
CN106980692B (en) | Influence calculation method based on microblog specific events | |
CN103678670B (en) | Micro-blog hot word and hot topic mining system and method | |
CN103745000B (en) | Hot topic detection method of Chinese micro-blogs | |
CN104504150B (en) | News public sentiment monitoring system | |
CN103514183B (en) | Information search method and system based on interactive document clustering | |
CN103778186B (en) | A kind of detection method of " network waistcoat " | |
Sharifi et al. | Summarization of twitter microblogs | |
CN106940732A (en) | A kind of doubtful waterborne troops towards microblogging finds method | |
CN109086375B (en) | Short text topic extraction method based on word vector enhancement | |
CN105095419B (en) | A kind of informational influence power maximization approach towards microblogging particular type of user | |
CN102194012B (en) | Microblog topic detecting method and system | |
CN103761239A (en) | Method for performing emotional tendency classification to microblog by using emoticons | |
CN106780073A (en) | A kind of community network maximizing influence start node choosing method for considering user behavior and emotion | |
CN107066555A (en) | Towards the online topic detection method of professional domain | |
Liao et al. | Coronavirus pandemic analysis through tripartite graph clustering in online social networks | |
CN102662987B (en) | A kind of sorting technique of the network text semanteme based on Baidupedia | |
CN109726402A (en) | A kind of document subject matter word extraction method | |
CN110929683B (en) | Video public opinion monitoring method and system based on artificial intelligence | |
CN105869058A (en) | Method for user portrait extraction based on multilayer latent variable model | |
CN105989033A (en) | Information duplication eliminating method based on information fingerprints | |
Daouadi et al. | Organization vs. Individual: Twitter User Classification. | |
CN105302866A (en) | OSN community discovery method based on LDA Theme model | |
Chakraborty et al. | Detection of fake users in twitter using network representation and nlp | |
Campbell et al. | Content+ context networks for user classification in twitter |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |